What is design-control-loop?

A plugin for designing and building an agentic control loop: a repeating system where sensors observe a codebase, a controller decides what to do, and an actuator makes changes. It includes a design interview and locally runnable components with a scheduled GitHub Actions workflow.

Use it to design recurring coding-agent automation for a repository, define observation and decision steps, build local loop components, and run the process through scheduled GitHub Actions.

It helps turn an ongoing coding task into a repeatable process that can observe changes, make decisions, and act on a schedule. The control-loop model also accounts for disturbances that may affect the work.

design-control-loop — Plugin by humanlayer

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add humanlayer/skills

agentmods

npx agentmods add plugins/humanlayer/skills/design-control-loop

Clone the repo

git clone --depth 1 https://github.com/humanlayer/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

design-control-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/design-control-loop/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "design-control-loop",
  "description": "Interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) for their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow",
  "version": "1.0.0",
  "author": {
    "name": "humanlayer",
    "email": "[email protected]"
  },
  "repository": "https://github.com/humanlayer/skills",
  "license": "MIT",
  "keywords": ["control-loop", "control-theory", "sensor-controller-actuator", "iterated-agentic-loop", "coding-agents", "github-actions", "skills", "claude-code"]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 13 lines scan A ed8adef5adb9

Subscribe to this mod's changes

design-control-loop is a plugin published in the GitHub repository humanlayer/skills (615 stars, last pushed 19d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Productivity

design-control-loop

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc

ecc